© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 119734
    Prev
    Next
    INDEX
    Explanations

    citations of scientific references, particularly in physics-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     few
    -0.07
    Few
    -0.07
    ech
    -0.07
    å°ij
    -0.07
     only
    -0.06
     Few
    -0.06
    only
    -0.06
    ead
    -0.06
     vc
    -0.06
     Minh
    -0.06
    POSITIVE LOGITS
    itom
    0.08
    quares
    0.07
    itol
    0.06
    opa
    0.06
    etable
    0.06
    urement
    0.06
    fffffff
    0.06
    ÑĮÑİ
    0.06
    arat
    0.06
    ingleton
    0.06
    Activations Density 0.006%

    No Known Activations